© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126570
    Prev
    Next
    INDEX
    Explanations

    references to books and literature, particularly emphasizing their diversity and relevance to readers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĻez
    -0.08
    _Lean
    -0.07
    charm
    -0.07
    dia
    -0.07
    -www
    -0.07
    voje
    -0.07
    inalg
    -0.07
    subst
    -0.07
    .realm
    -0.07
    onu
    -0.07
    POSITIVE LOGITS
    ycz
    0.06
     Gravity
    0.05
    ah
    0.05
    echa
    0.05
    sb
    0.05
     m
    0.05
     t
    0.05
     arg
    0.05
     ii
    0.05
    ii
    0.05
    Activations Density 0.001%

    No Known Activations